Paper:
Language: English:

A Classifier Based on Neuro-Fuzzy Inference System Ernest

Czogala^, Jacek Leski^, and Yoichi Hayashi^**

*Institute of Electronics, Technical University of Silesia Akademicka 16, 44-101 Gliwice, Poland
**Department of Computer Science, Meiji University 1-1-1 Higashimita, Tama-ku, Kawasaki 214-8571, Japan

Received: January 10, 1999

Accepted: June 21, 1999

Keywords: Neuro-fuzzy inference system, If-then rules, Fuzzy classifier, Pattern recognition

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.3, No.4 pp. 282-288, 1999

Abstract

In this paper a new classifier based on fuzzy inference system has been described. The novelty of the classifier consists in the moving fuzzy consequent in if-then rules and in selection method of target values for classifier outputs minimizing the number of false classifications. The location of fuzzy set in conclusion is determined by a linear combination of system inputs. The method of classifier construction for two classes and an extension for a greater number of classes has been presented. The tests of the new classifier are carried out on the basis of the data bases known from literature: forensic glass and iris.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: